Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add IchenDEV/prompt-optimizer-plugins --skill optimize-gpt-6-astra-promptsgit clone --depth 1 https://github.com/IchenDEV/prompt-optimizer-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ichendev/prompt-optimizer-plugins/optimize-gpt-6-astra-prompts)<a href="https://agentmods.dev/skills/ichendev/prompt-optimizer-plugins/optimize-gpt-6-astra-prompts"><img src="https://agentmods.dev/badge/skills/ichendev/prompt-optimizer-plugins/optimize-gpt-6-astra-prompts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ichendev/prompt-optimizer-plugins/optimize-gpt-6-astra-prompts"><img src="https://agentmods.dev/badge/skills/ichendev/prompt-optimizer-plugins/optimize-gpt-6-astra-prompts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00134 | $0.02089 |
| Opus 5 | $0.00067 | $0.01045 |
| Sonnet 5 | $0.00027 | $0.00418 |
| Haiku 4.5 | $0.00013 | $0.00209 |
Grade A, and why
optimize-gpt-6-astra-prompts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize GPT-6 Astra Prompts
Turn rough ideas and existing prompt stacks into copy-ready GPT-6 Astra prompts. Preserve the user's intent and hard constraints, ask for genuinely blocking information, and apply Astra-specific mitigations only where the task or observed behavior requires them.
Use the official basis
Read references/official-guidance.md when model-specific rationale, API-setting guidance, migration notes, or the longer checklist is needed. Treat its URLs as canonical sources and its prose as a dated summary. Fetch the live OpenAI pages before making claims about the current model alias, parameters, availability, or other facts that may change.
For cleaning repository Skills, AGENTS.md, or Sol-era coding-agent scaffolding (wrong skill loads, full-repo pre-reads, over-testing, early stops), use $audit-gpt-6-astra-skills instead of stuffing harness cleanup into a prompt rewrite.
Follow the workflow
1. Capture the prompt contract
Identify the following from the user's message, pasted prompt, or referenced file:
- intended user-visible outcome;
- inputs and context the model will receive;
- hard constraints and facts to preserve;
- required output shape, audience, and language;
- evidence, tool use, or validation needed for success;
- side effects the model may take and actions that require approval;
- autonomy level: when to ask, when to persist, and when approval is the final step;
- fallback or stopping behavior when required information is unavailable.
Treat these as diagnostic dimensions, not mandatory sections. Keep a simple rewriting prompt simple.
If the user supplies a layered prompt stack, preserve the separation between system, developer, user, and tool-description content. Do not silently move instructions between trust levels.
2. Apply the clarity gate
Ask a question only when the missing or conflicting information is blocking: two reasonable answers would lead to materially different prompts, outputs, permissions, or success criteria.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +2 lines e25f7e5989a9
- 6d ago First seen · 138 lines · 134 tokens per session scan A fdf49ead7e4f
optimize-gpt-6-astra-prompts is a skill published in the GitHub repository IchenDEV/prompt-optimizer-plugins (6 stars, last pushed 4d ago), licensed MIT. It adds 134 tokens to every session and 2,089 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
build-dotnet-agent-service
Build a local-first F# or C# Semantic Kernel agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
analyze-prompt
Use when the user wants to review, score, or improve how they write prompts; when coaching prompt quality; or when tracking prompting mistakes over a session. Keywords: prompt analysis, prompt coaching, how should I ask, rate my prompt, am I prompting well, prompt statistics, prompt score.
prompt-mini
Forges weak Claude Code prompts into structured, credit-saving, framework-aware prompts. Use when prompts are vague, missing scope, or mention a stack without clear task definition.
gpt-5-6-prompt-engine
Use when creating, auditing, rewriting, debugging, migrating, or evaluating GPT-5.6 Sol, Terra, or Luna prompt layers, tool descriptions, agent briefs, or prompt stacks; choosing runtime configuration; or comparing controlled prompt candidates.